chipnemo-domain-adapted-llms-for-chip-design-exploration

enhancing-robotic-grasping-in-dynamic-environments

puma-decentralized-multiagent-trajectory-planner-with-image-segmentation-based-frame-alignment

analyzing-matrices-over-polynomial-rings-with-restricted-subdeterminants

approximate-multiagent-reinforcement-learning-for-urban-mobility-problem

retinal-oct-synthesis-using-ddpm-for-layer-segmentation

can-large-language-models-llms-follow-simple-rules-

modeling-user-viewing-flow-using-large-language-models-for-article-recommendation


This paper proposes a procedural method to generate large-scale synthetic datasets with diverse human-object interactions, and a hierarchical diffusion model that can reconstruct accurate 3D human and object shapes without relying on predefined templates.


coremsg

procedural-generation-of-diverse-human-object-interaction-datasets-for-robust-3d-reconstruction


Procedural Generation of Diverse Human-Object Interaction Datasets for Robust 3D Reconstruction


title_rewrite

Template-free 3D reconstruction of human and object from single RGB image